If your Neural Network model seems to have high variance, what of the following would be promising things to try?

Make the Neural Network deeper

N

Get more training data

Y

Get more test data

N

Add regularization

Y

Increase the number of units in each hidden layer

N

You are working on an automated check-out kiosk for a supermarket, and are building a classifier for apples, bananas and oranges. Suppose your classifier obtains a training set error of 0.5%, and a dev set error of 7%. Which of the following are promising things to try to improve your classifier? (Check all that apply.)

Increase the regularization parameter lambda

Y

Decrease the regularization parameter lambda

N

Get more training data

Y

Use a bigger neural network

N

Practical aspects of deep learning的更多相关文章

  1. [C2W1] Improving Deep Neural Networks : Practical aspects of Deep Learning

    第一周:深度学习的实用层面(Practical aspects of Deep Learning) 训练,验证,测试集(Train / Dev / Test sets) 本周,我们将继续学习如何有效运 ...

  2. 吴恩达《深度学习》-第二门课 (Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization)-第一周：深度学习的实践层面 (Practical aspects of Deep Learning) -课程笔记

    第一周:深度学习的实践层面 (Practical aspects of Deep Learning) 1.1 训练,验证,测试集(Train / Dev / Test sets) 创建新应用的过程中, ...

  3. 吴恩达《深度学习》-课后测验-第二门课 (Improving Deep Neural Networks:Hyperparameter tuning, Regularization and Optimization)-Week 1 - Practical aspects of deep learning（第一周测验 - 深度学习的实践）

    Week 1 Quiz - Practical aspects of deep learning(第一周测验 - 深度学习的实践) \1. If you have 10,000,000 example ...

  4. 课程二(Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization)，第一周（Practical aspects of Deep Learning） —— 4.Programming assignments:Gradient Checking

    Gradient Checking Welcome to this week's third programming assignment! You will be implementing grad ...

  5. Improving Deep Neural Networks: Hyperparameter tuning, Regularization and Optimization（第一周）深度学习的实践层面 (Practical aspects of Deep Learning)

    1. Setting up your Machine Learning Application 1.1 训练,验证,测试集(Train / Dev / Test sets) 1.2 Bias/Vari ...

  6. [C3] Andrew Ng - Neural Networks and Deep Learning

    About this Course If you want to break into cutting-edge AI, this course will help you do so. Deep l ...

  7. 最实用的深度学习教程 Practical Deep Learning For Coders (Kaggle 冠军 Jeremy Howard 亲授)

    Jeremy Howard 在业界可谓大名鼎鼎.他是大数据竞赛平台 Kaggle 的前主席和首席科学家.他本人还是 Kaggle 的冠军选手.他是美国奇点大学(Singularity Universi ...

  8. Why Deep Learning Works – Key Insights and Saddle Points

    Why Deep Learning Works – Key Insights and Saddle Points A quality discussion on the theoretical mot ...

  9. 【深度学习Deep Learning】资料大全

    最近在学深度学习相关的东西,在网上搜集到了一些不错的资料,现在汇总一下: Free Online Books  by Yoshua Bengio, Ian Goodfellow and Aaron C ...

随机推荐

  1. bbs系统的相关知识点

    1.注册功能 1.注册功能往往都会由很多校验性的需求 所以这里我们用到了forms组件 项目中可能有多个地方需要用到不同的forms组件 为了解耦合 但是创建一个py文件 专门用来存放项目用到的所有的 ...

  2. 【音乐欣赏】《Siren》 - The Chainsmokers / Aazar

    曲名:Siren 作者:The Chainsmokers . Aazar [00:00.00] 作曲 : Alex Pall/Andrew Taggart/Alexis Duvivier [00:01 ...

  3. C#系统库的源代码

    .NET Core:https://github.com/dotnet/corefx .NET Framework:https://referencesource.microsoft.com

  4. 基于jenkins自动打包并部署docker环境及PHP环境

  5. Linux centos7 shell 介绍、 命令历史、命令补全和别名、通配符、输入输出重定向

    一.shell介绍 shell脚本是日常Linux系统管理工作中必不可少的,不会shell,就不是一个合格管理员. shell是系统跟计算机硬件交互使用的中间介质,一个系统工具.实际上在shell和计 ...

  6. c# pcm

    using System; using System.IO; using System.Text; using System.Windows.Forms; using System.Runtime.I ...

  7. 方便的 IcoMoon 图标字体

    官网地址:https://icomoon.io/app/#/select 已发现的方便之处: 1.官网已提供大量常用图标字体: 2.可通过 svg 将其转换为 图标字体: 3.不仅可转换,还可自定义编 ...

  8. [Fiddler学习] - Mock的简单实现原理及方法

    最近在研究Fidder抓包并做一点测试工作,下面介绍一下Fiddler的实现原理: 简单来说从clent,server端发出来的请求,都需要通过Fiddler进行代理走一遍.如果有任何请求需要做修改, ...

  9. django admin后台（数据库简单管理后台）

    只需要简单的几行胆码就可以生成一个完整的管理后台 这个就是django魅力之一 创建超级用户 python manage.py createsuperuser     ----  之后会提示输入用慕名 ...

  10. 如何利用wx.request进行post请求

    1,method 是  get  方式的时候,会将数据转换成 query string method 为 post 时,header为{"Content-Type": " ...